INDEX

Explanations

numerical figures and statistics

oai_token-act-pair · gpt-3.5-turbo

references to quantitative data and statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.84

NetMessage

-0.81

Pros

-0.71

ricular

-0.67

 Recipes

-0.67

 Conditions

-0.65

 VIDEOS

-0.63

romy

-0.61

saf

-0.61

 physic

-0.61

POSITIVE LOGITS

 estimates

1.07

 exceeds

1.04

 excludes

1.01

 exceeded

1.01

includes

1.01

 dwar

0.99

 totaled

0.97

 estimate

0.95

 fluct

0.91

 varies

0.90

Activations Density 0.219%

numerical figures and statistics

references to quantitative data and statistics

No Comments

No Known Activations